Article Text

Download PDFPDF

LSO-080 Machine-learning approach on lupus low disease activity prediction
  1. Nick Faelnar1,
  2. Michael Tee1,
  3. Cherica Tee1,
  4. Jaime Caro1,
  5. Geoffrey Solano1,
  6. Rangi Kandane-Rathnayake2,
  7. Angelene Therese Magbitang-Santiago1,
  8. Evelyn Salido1,
  9. Vera Golder2,
  10. Worawit Louthrenoo3,
  11. Yi-Hsing Chen4,
  12. Jiacai Cho5,
  13. Aisha Lateef5,
  14. Laniyati Hamijoyo6,
  15. Shue-Fen Luo7,
  16. Yeong-Jian J Wu7,
  17. Sandra Navarra8,
  18. Leonid Zamora8,
  19. Zhanguo Li9,
  20. Sargunan Sockalingam10,
  21. Yasuhiro Katsumata11,
  22. Masayoshi Harigai11,
  23. Yanjie Hao12,
  24. Zhuoli Zhang12,
  25. BMDB Basnayake13,
  26. Madelynn Chann14,
  27. Jun Kikuchi15,
  28. Tsutomu Takeuchi15,16,
  29. Sang-Cheol Bae17,
  30. Shereen Oon18,
  31. Sean O’Neill19,
  32. Fiona Goldblatt20,
  33. Kristine Ng21,
  34. Annie Law22,
  35. Nicola Tugnet23,
  36. Sunil Kumar24,
  37. Naoaki Ohkubo25,
  38. Yoshiya Tanaka25,
  39. Chak Sing Lau26,
  40. Mandana Nikpour18,
  41. Alberta Hoi2 and
  42. Eric Morand2
  1. 1University of the Philippines, Philippines
  2. 2Monash University, Australia
  3. 3Faculty of Medicine, Chiang Mai University, Thailand
  4. 4Taichung Veterans General Hospital, Taiwan
  5. 5National University Hospital, Singapore
  6. 6University of Padjadjaran, Indonesia
  7. 7Chang Gung Memorial Hospital, Taiwan
  8. 8University of Santo Tomas Hospital, Philippines
  9. 9People’s Hospital Peking University Health Sciences Centre, China
  10. 10University of Malaya, Malaysia
  11. 11Tokyo Women’s Medical University, Japan
  12. 12Peking University First Hospital, China
  13. 13Teaching Hospital, SriLanka
  14. 14Tan Tock Seng Hospital, Singapore
  15. 15Keio University, Japan
  16. 16Saitama Medical University, Japan
  17. 17Hanyang University Institute for Rheumatology Research, Republic of Korea
  18. 18The University of Melbourne at St Vincent’s Hospital, Australia
  19. 19University of New South Wales and Ingham Institute of Applied Medical Research, Australia
  20. 20Royal Adelaide Hospital and Flinders Medical Centre, Australia
  21. 21Waitemata District Health Board, New Zealand
  22. 22Singapore General Hospital, Singapore
  23. 23Auckland District Health Board, New Zealand
  24. 24Middlemore Hospital, New Zealand
  25. 25University of Occupational and Environmental Health, Japan
  26. 26University of Hong Kong, Hong Kong


Background The development of lupus low disease activity state (LLDAS) as a treat-to-target endpoint for SLE patients has been validated. Its attainment has been associated with improved outcomes. This study aims to show whether a machine learning model can yield good results in predicting whether a patient will achieve LLDAS on their succeeding assessment.

Methods A total of 42,355 records of patients were retrieved from the APLC longitudinal study database. Three machine learning models – XGBoost, Random Forest, and Naive Bayes – were tested for their predictive power. Eighty percent of the data was used to train the models while thirty percent was used for validation. The data were normalized and all models were subjected to 10-fold cross-validation to prevent overfitting. Additionally, we compared the top ten most significant features of each model.

Results Various metrics were used to measure the model’s predictive power. The results of our study showed that the Random Forest model scored the highest for specificity, PPV, and accuracy with 0.8450, 0.8182, and 0.8338, respectively. The XGBoost model topped the NPV metric with 0.8559 while the Naive Bayes model got the highest score for sensitivity with 0.8986. It is good to note that the score difference of Random Forest with the top sensitivity and NPV scores were only 0.0629 and 0.0085, respectively.

For the significant features, only two features were present on all three models, namely the current LLDAS and proteinuria level. Three additional features were important for two models—whether the patient is taking prednisolone; time adjusted mean (TAM) SLEDAI score; and SLEDAI score.

Conclusions The study showed and compared various machine learning models on their predictive power in determining whether a patient will achieve LLDAS on their next visit. The results determined that the current LLDAS, proteinuria levels, SLEDAI score (and TAM SLEDAI),

  • Systemic lupus erythematosus
  • Lupus low disease activity state
  • Machine learning

This is an open access article distributed in accordance with the Creative Commons Attribution Non Commercial (CC BY-NC 4.0) license, which permits others to distribute, remix, adapt, build upon this work non-commercially, and license their derivative works on different terms, provided the original work is properly cited, appropriate credit is given, any changes made indicated, and the use is non-commercial. See:

Statistics from

Request Permissions

If you wish to reuse any or all of this article please use the link below which will take you to the Copyright Clearance Center’s RightsLink service. You will be able to get a quick price and instant permission to reuse the content in many different ways.